Comparison Of A Hybrid Neural Network And Semi-Distributed Simulator For Stream Flow Prediction

Lariyah Mohd Sidek, Milad Jajarmizadeh, Sobri Harun, Shamsuddin Shahid, Hidayah Basri

Research output: Contribution to conferencePaper

4 Downloads (Pure)

Abstract

Hydrological models are widely used for the simulation of stream flow in order to aid
water resources planning and management in catchment or river basin. Numerous
hydrological models have been developed based on different theories. Performance of
such models depends on hydroclimatic
setting of a catchment. In the present study,
performance of a widely used physically based distributed model known as Soil and
Water Assessment (SWAT) and a datadriven
model, namely hybrid artificial neural
network (HANN), has been evaluated to simulate stream flow in an arid catchment
located in the south of Iran. Data related to topography, hydrometeorology, land cover,
and soil were collected and processed for this purpose. The models were calibrated and
validated with same time period to evaluate the advantage and disadvantages of
different models. The results showed SWAT outperformed HANN in terms of relative
errors such as NashSutcliffe
efficiency and percent of bias during model validation.
Other error indicates, namely root mean square error (RMSE), mean square error, and
mean relative error (MRE), were found close to zero for SWAT during both model
calibration and validation. The study suggests that both models have their own
promising flow prediction due to their own features and capabilities for daily flow.
Original languageEnglish
Pages115-127
Number of pages12
DOIs
Publication statusAccepted/In press - 10 Apr 2016

Fingerprint

Stream flow
Simulator
Simulators
Neural Networks
Neural networks
Soil
Prediction
Catchments
Soils
Mean square error
Model
Land Cover
Model Validation
Performance Model
Topography
Relative Error
Percent
Planning
Roots
Resources

All Science Journal Classification (ASJC) codes

  • Modelling and Simulation

Cite this

@conference{fed3e67585c34a70a349fdc290d8698e,
title = "Comparison Of A Hybrid Neural Network And Semi-Distributed Simulator For Stream Flow Prediction",
abstract = "Hydrological models are widely used for the simulation of stream flow in order to aidwater resources planning and management in catchment or river basin. Numeroushydrological models have been developed based on different theories. Performance ofsuch models depends on hydroclimaticsetting of a catchment. In the present study,performance of a widely used physically based distributed model known as Soil andWater Assessment (SWAT) and a datadrivenmodel, namely hybrid artificial neuralnetwork (HANN), has been evaluated to simulate stream flow in an arid catchmentlocated in the south of Iran. Data related to topography, hydrometeorology, land cover,and soil were collected and processed for this purpose. The models were calibrated andvalidated with same time period to evaluate the advantage and disadvantages ofdifferent models. The results showed SWAT outperformed HANN in terms of relativeerrors such as NashSutcliffeefficiency and percent of bias during model validation.Other error indicates, namely root mean square error (RMSE), mean square error, andmean relative error (MRE), were found close to zero for SWAT during both modelcalibration and validation. The study suggests that both models have their ownpromising flow prediction due to their own features and capabilities for daily flow.",
author = "{Mohd Sidek}, Lariyah and Milad Jajarmizadeh and Sobri Harun and Shamsuddin Shahid and Hidayah Basri",
year = "2016",
month = "4",
day = "10",
doi = "10.1007/9789811005008_ 10",
language = "English",
pages = "115--127",

}

Comparison Of A Hybrid Neural Network And Semi-Distributed Simulator For Stream Flow Prediction. / Mohd Sidek, Lariyah; Jajarmizadeh, Milad; Harun, Sobri; Shahid, Shamsuddin ; Basri, Hidayah.

2016. 115-127 .

Research output: Contribution to conferencePaper

TY - CONF

T1 - Comparison Of A Hybrid Neural Network And Semi-Distributed Simulator For Stream Flow Prediction

AU - Mohd Sidek, Lariyah

AU - Jajarmizadeh, Milad

AU - Harun, Sobri

AU - Shahid, Shamsuddin

AU - Basri, Hidayah

PY - 2016/4/10

Y1 - 2016/4/10

N2 - Hydrological models are widely used for the simulation of stream flow in order to aidwater resources planning and management in catchment or river basin. Numeroushydrological models have been developed based on different theories. Performance ofsuch models depends on hydroclimaticsetting of a catchment. In the present study,performance of a widely used physically based distributed model known as Soil andWater Assessment (SWAT) and a datadrivenmodel, namely hybrid artificial neuralnetwork (HANN), has been evaluated to simulate stream flow in an arid catchmentlocated in the south of Iran. Data related to topography, hydrometeorology, land cover,and soil were collected and processed for this purpose. The models were calibrated andvalidated with same time period to evaluate the advantage and disadvantages ofdifferent models. The results showed SWAT outperformed HANN in terms of relativeerrors such as NashSutcliffeefficiency and percent of bias during model validation.Other error indicates, namely root mean square error (RMSE), mean square error, andmean relative error (MRE), were found close to zero for SWAT during both modelcalibration and validation. The study suggests that both models have their ownpromising flow prediction due to their own features and capabilities for daily flow.

AB - Hydrological models are widely used for the simulation of stream flow in order to aidwater resources planning and management in catchment or river basin. Numeroushydrological models have been developed based on different theories. Performance ofsuch models depends on hydroclimaticsetting of a catchment. In the present study,performance of a widely used physically based distributed model known as Soil andWater Assessment (SWAT) and a datadrivenmodel, namely hybrid artificial neuralnetwork (HANN), has been evaluated to simulate stream flow in an arid catchmentlocated in the south of Iran. Data related to topography, hydrometeorology, land cover,and soil were collected and processed for this purpose. The models were calibrated andvalidated with same time period to evaluate the advantage and disadvantages ofdifferent models. The results showed SWAT outperformed HANN in terms of relativeerrors such as NashSutcliffeefficiency and percent of bias during model validation.Other error indicates, namely root mean square error (RMSE), mean square error, andmean relative error (MRE), were found close to zero for SWAT during both modelcalibration and validation. The study suggests that both models have their ownpromising flow prediction due to their own features and capabilities for daily flow.

U2 - 10.1007/9789811005008_ 10

DO - 10.1007/9789811005008_ 10

M3 - Paper

SP - 115

EP - 127

ER -